Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.
Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.
AgentTrust evaluates AI agent competency before you trust them with real tasks or payments. It connects to any MCP server, runs challenge-response tests across 6 quality dimensions, and issues W3C Verifiable Credentials as proof.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
| Variable | Description | Required |
|---|---|---|
| GROQ_API_KEY | Credential the server authenticates with. | Yes |
| CEREBRAS_API_KEY | Credential the server authenticates with. | Yes |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Hot-reload your MCP servers without restarting your AI coding assistant. Works excellently with VSCode MCP, well with Claude Code. A transparent
Scope-gated Linear project administration with optional GitHub and Obsidian evidence adapters
Formula One MCP server using FastF1
A **production-ready Model Context Protocol (MCP) server** that enables LLMs (Claude, Copilot, Cursor, etc.) to automate **SAP GUI** using the